Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 18798
    Prev
    Next
    INDEX
    Explanations

    entities or individuals who specialize in specific fields or activities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specialization in various fields or professions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iron
    -0.64
    forth
    -0.63
    riel
    -0.63
    vious
    -0.63
     Bagg
    -0.62
    ermanent
    -0.61
    à¥
    -0.60
     Goodbye
    -0.60
    runner
    -0.60
     goodbye
    -0.59
    POSITIVE LOGITS
     specialize
    0.99
     specializes
    0.94
    rador
    0.84
     specializing
    0.82
     specialized
    0.80
    nels
    0.79
     specialty
    0.78
    sonian
    0.77
    anooga
    0.74
    £ı
    0.71
    Activations Density 0.014%

    No Known Activations